LLM Reference

Inkling Models by Thinking Machines Lab

Thinking Machines LabApache 2.0Open source
1 model2026Up to 1m ctxFrom $1/1M input

Last refreshed 2026-07-15. Next refresh: weekly.

Details

LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context1m

Capabilities

VisionAll models
MultimodalAll models
ReasoningAll models
JSON / Tool useAll models

About

Inkling is Thinking Machines Lab's open-weight general-purpose multimodal model family. Its initial 975B-total-parameter Mixture-of-Experts model accepts text, image, and audio inputs and produces text output with a 1M-token context window and controllable thinking effort. Compare it for Coding, RAG, Agents, Long context, Vision, and JSON / Tool use.

Decision facts

Best fit
vision and multimodal workreasoningJSON / Tool use
Capability starting point
Inkling with 1m context and reasoning, JSON / Tool use, and multimodal inputs
Lowest tracked input
Inkling · $1/1M · Baseten API
Closest related family
Claude 3

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view
InklingCurrent

Use when the workload needs 1m context, reasoning, and JSON / Tool use.

2026-071m contextreasoningJSON / Tool use

Release Timeline

1 release group
2026-07
1 current
Inkling
1m contextreasoningJSON / Tool use
Current

Specifications(1 models)

Inkling model specifications comparison
ModelReleasedContextParametersVisionMultimodalReasoningJSON / Tool use
Inkling2026-071m975B total, 41B activeYesYesYesYes

Available From(2 providers)

Pricing

Inkling model pricing by provider
ModelProviderInput / 1MOutput / 1MType
InklingBaseten API$1$4.05Serverless
InklingTinker$1.87$4.68Provisioned